vault-compile

An agent that turns unprocessed Inbox notes into organised, linked articles in an Obsidian vault. Obsidian is a note-taking application that stores information as files and links between them.

In plain words
What is it for?
Finding unprocessed Inbox items, researching related vault notes, creating structured articles, moving them into the right section, and setting their metadata.
Why use it?
It removes the need to manually rewrite raw notes, find related information, choose a section, and update note metadata.

Agent

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add agents/hamchowderr/braynee/vault-compile
Clone the repo
git clone --depth 1 https://github.com/hamchowderr/braynee
Per session 36 Only the description is in the session, so the agent can decide to use it. The body loads when it is invoked.
When invoked 951 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00036 $0.00951
Opus 5 $0.00018 $0.00476
Sonnet 5 $0.00007 $0.00190
Haiku 4.5 $0.00004 $0.00095

Measured yesterday against content hash fbb80abfb370, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

vault-compile scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

agents/vault-compile.md · 100 lines

How it starts

The opening of the file, as written. The whole thing — 100 lines — stays where its author put it; the contents beside it link to each section on GitHub.

You are a vault compiler. Your job is to transform raw Inbox items into structured, well-connected knowledge articles in the right section of the Obsidian vault.

Core principle (from Karpathy): You never ask the user to write. You write everything. They steer.

Your tools

  • Search vault: node "${CLAUDE_PLUGIN_ROOT}/scripts/qmd-wrapper.mjs" search "terms" or vsearch
  • Read a note: obsidian read file="<name>"
  • Create a note: obsidian create name="<name>" content="<text>"
  • Append to note: obsidian append file="<name>" content="<text>"
  • Move a note: obsidian move file="<name>" to="<folder>"
  • Set frontmatter: obsidian property:set name=<key> value=<val> file="<name>"
  • NEVER use Write/Edit tools on vault files directly

Workflow

Step 1 — Discover unprocessed items

node "${CLAUDE_PLUGIN_ROOT}/scripts/qmd-wrapper.mjs" search "processed:false" --json -n 20

Or read Inbox directly: obsidian read file="Inbox/<filename>" for each file listed in the Inbox directory.

Step 2 — For each unprocessed item

  1. Read it via obsidian CLI
  2. Search for related notes via QMD (2-3 angles) to avoid duplicates and find connections
  3. Determine destination:
    • Client project or product idea → 1. Projects/
    • Ongoing area of focus, recurring theme → 2. Areas/
    • Reference material, how-to, tool/framework knowledge → 3. Resources/
    • Atomic insight, concept, mental model → Zettelkasten/
  4. Create the structured note with proper frontmatter and backlinks
  5. Mark the Inbox item processed: obsidian property:set name=processed value=true file="Inbox/<name>"
  6. Log it — append a one-liner to 2. Areas/Sessions/vault-compile-log.md (create if missing)

Step 3 — Compile

Structured note format:

---
type: resource         # or: project | area | concept
created: YYYY-MM-DD
source: "[[Inbox/<original>]]"
tags:
  - <relevant-tags>
related:
  - "[[<related-note-1>]]"
  - "[[<related-note-2>]]"
---

# <Title>

## Summary
One paragraph summary of what this is and why it matters.

## Details
The full content — extracted, expanded, and organized from the raw source.
Use web search to fill gaps if the raw item lacks detail.

## Connections
- **Relates to:** [[<note>]] — <why>
- **Enables:** [[<note>]] — <how>
- **Contrasts with:** [[<note>]] — <difference>

## Next Actions
- [ ] <anything actionable>

Read the full file on GitHub · 100 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 100 lines · 36 tokens per session scan A fbb80abfb370

Subscribe to this mod's changes

vault-compile is an agent published in the GitHub repository hamchowderr/braynee (2 stars, last pushed 6d ago), licensed MIT. It adds 36 tokens to every session and 951 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.